* </p>
 *
 * <p>
 * The crawling process involves the following steps:
 * </p>
 * <ol>
 *   <li>Fetching a URL from the queue using {@link UrlQueueService#poll(String)}.</li>
 *   <li>Checking if the URL is valid using {@link #isValid(UrlQueue)}.</li>
 *   <li>Accessing the content using a {@link CrawlerClient} obtained from {@link CrawlerClientFactory}.</li>

     * This class handles the authentication, connection management, and data retrieval
     * from storage buckets and objects.
     *
     * <p>
     * The connection extracts bucket and object names from the URL and uses environment
     * variables for authentication and endpoint configuration.
     * </p>
     */

        return processRequest(uri, true);
    }

    /**
     * Processes an FTP request to retrieve data from the specified URI.
     * This method handles the complete FTP request lifecycle including timeout management,
     * connection setup, and data retrieval.
     *
     * @param uri The URI to retrieve data from
     * @param includeContent Whether to include the actual content in the response

    /**
     * The name of the component to be retrieved from the CrawlerContainer.
     */
    protected String componentName;

    /**
     * The listener that is called when a pooled object is destroyed.
     */
    protected OnDestroyListener<T> onDestroyListener;

    /**
     * Creates a new object instance from the crawler container.

 * and registration with the ExtractorFactory.
 *
 * <p>
 * This class handles the retrieval of essential crawler components like
 * {@link MimeTypeHelper} and {@link ExtractorFactory} from the
 * {@link CrawlerContainer}. It also provides a convenient method for
 * registering the extractor with the {@link ExtractorFactory}.
 * </p>
 *
 * <p>

 *   <li><b>trimSpaceEnabled:</b> A flag to enable or disable trimming of whitespace from extracted values.</li>
 *   <li><b>charsetName:</b> The character encoding for the output XML.</li>
 *   <li><b>dataClass:</b> The class type to return from the {@link #getData(AccessResultData)} method.</li>
 * </ul>
 *
 */
public class XpathTransformer extends HtmlTransformer {

    /**

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {
        super();
    }

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.

     * @param url the URL to be excluded
     */
    void addExcludeUrlFilter(String sessionId, String url);

    /**
     * Adds a list of URLs to be excluded from crawling for a specific session.
     *
     * @param sessionId the ID of the session for which the URLs should be excluded
     * @param urlList the list of URLs to be excluded
     */

    private final File tempFile;

    private final FileInputStream fileInputStream;

    /**
     * A class that provides an input stream for reading from a temporary file.
     * This class wraps a {@link FileInputStream} to read from the specified temporary file.
     *
     * @param tempFile the temporary file to be read
     * @throws FileNotFoundException if the specified file does not exist
     */

/**
 * Gets a text from . file.
 *
 * @author shinsuke
 *
 */
public class MsPublisherExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPublisherExtractor instance.
     */
    public MsPublisherExtractor() {
        super();
    }

    /**
     * Extracts text from the Publisher input stream.
     * @param in The input stream.